\(t\) test example using nycflights13
flights
data" />
nycflights13
flights
datavignettes/two_sample_t.Rmd
two_sample_t.Rmd
Note: The type
argument in generate()
is automatically filled based on the entries for specify()
and hypothesize()
. It can be removed throughout the examples that follow. It is left in to reiterate the type of generation process being performed.
library(nycflights13)
library(dplyr)
library(stringr)
library(infer)
set.seed(2017)
fli_small <- flights %>%
sample_n(size = 500) %>%
mutate(half_year = case_when(
between(month, 1, 6) ~ "h1",
between(month, 7, 12) ~ "h2"
)) %>%
mutate(day_hour = case_when(
between(hour, 1, 12) ~ "morning",
between(hour, 13, 24) ~ "not morning"
)) %>%
select(arr_delay, dep_delay, half_year,
day_hour, origin, carrier)
arr_delay
, dep_delay
half_year
("h1"
, "h2"
),day_hour
("morning"
, "not morning"
)origin
("EWR"
, "JFK"
, "LGA"
)carrier
The recommended approach is to use specify() %>% calculate()
:
obs_t <- fli_small %>%
specify(arr_delay ~ half_year) %>%
calculate(stat = "t", order = c("h1", "h2"))
## Warning: Removed 15 rows containing missing values.
The observed \(t\) statistic is 0.8685463.
Or using t_test
in infer
obs_t <- fli_small %>%
t_test(formula = arr_delay ~ half_year, alternative = "two_sided",
order = c("h1", "h2")) %>%
dplyr::select(statistic) %>%
dplyr::pull()
The observed \(t\) statistic is 0.8685463.
Or using another shortcut function in infer
:
obs_t <- fli_small %>%
t_stat(formula = arr_delay ~ half_year, order = c("h1", "h2"))
The observed \(t\) statistic is 0.8685463.
t_null_distn <- fli_small %>%
# alt: response = arr_delay, explanatory = half_year
specify(arr_delay ~ half_year) %>%
hypothesize(null = "independence") %>%
generate(reps = 1000, type = "permute") %>%
calculate(stat = "t", order = c("h1", "h2"))
## Warning: Removed 15 rows containing missing values.
t_null_distn %>% visualize(obs_stat = obs_t, direction = "two_sided")
t_null_distn %>%
get_pvalue(obs_stat = obs_t, direction = "two_sided")
## # A tibble: 1 x 1
## p_value
## <dbl>
## 1 0.430
fli_small %>%
# alt: response = arr_delay, explanatory = half_year
specify(arr_delay ~ half_year) %>%
hypothesize(null = "independence") %>%
# generate() ## Not used for theoretical
calculate(stat = "t", order = c("h1", "h2")) %>%
visualize(method = "theoretical", obs_stat = obs_t, direction = "two_sided")
## Warning: Removed 15 rows containing missing values.
## Warning: Check to make sure the conditions have been met for the
## theoretical method. {infer} currently does not check these for you.
fli_small %>%
# alt: response = arr_delay, explanatory = half_year
specify(arr_delay ~ half_year) %>%
hypothesize(null = "independence") %>%
generate(reps = 1000, type = "permute") %>%
calculate(stat = "t", order = c("h1", "h2")) %>%
visualize(method = "both", obs_stat = obs_t, direction = "two_sided")
## Warning: Check to make sure the conditions have been met for the
## theoretical method. `infer` currently does not check these for you.
fli_small %>%
t_test(formula = arr_delay ~ half_year,
alternative = "two_sided",
order = c("h1", "h2")) %>%
dplyr::select(p_value) %>%
dplyr::pull()
## [1] 0.3855325